A digital bit-reconfigurable versatile compute-in-memory macro for machine learning acceleration

• Main Authors: Zhang, Xin, Lu, Yuncheng, Wang, Bo, Kim, Tony Tae-Hyoung
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Electrical and electronic engineering; Computing-in-memory; Addition
• Online Access: https://hdl.handle.net/10356/170326
• Institution: Nanyang Technological University

This brief proposes a digital versatile SRAM-based computing-in-memory (CIM) macro with reconfigurable precision from 1-bit to 16-bit and programmable mathematical functions, including addition and multiplication. The proposed CIM macro supports 116-bit weight-stationary addition (WSA) and operands-stationary addition (OSA), and 18-bit bit-serial multiplication (BSM). The proposed versatile CIM macro accelerates various machine learning algorithms such as convolutional neural networks (CNNs) and self-organizing maps (SOMs). A test chip was fabricated in 65nm CMOS technology and achieved an energy efficiency of up to 40.7 TOPS/W for WSA (1-bit), 39.4TOPS/W for OSA (1-bit), and 84.1 TOPS/W for BSM (1-bit).